© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 49037
    Prev
    Next
    INDEX
    Explanations

    Macau and macarons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rawlings
    0.43
    AppState
    0.38
     РАН
    0.38
    悝
    0.37
     صد
    0.37
     стране
    0.37
    DUP
    0.37
    Train
    0.36
    sworth
    0.36
     भर्त
    0.36
    POSITIVE LOGITS
     Macau
    1.31
    氹
    1.07
    澳門
    1.06
    澳门
    0.96
    葡
    0.90
     Senado
    0.90
     Portuguese
    0.89
     गोवा
    0.88
     Mac
    0.83
     Goa
    0.82
    Activations Density 0.003%

    No Known Activations